Google launches Gemini Omni 1.2 Flash for longer, cheaper video generation
Google is rolling out Gemini Omni 1.2 Flash, a video generation model that can create clips of up to 15 seconds, follow references more closely and support conversational editing. The company says the update cuts the price by 30% from Gemini Omni 1.1, to $0.07 per second for 720p video.
- Gemini Omni 1.2 Flash generates and edits videos up to 15 seconds long.
- Google says the price is $0.07 per second for 720p video.
- The model supports multi-turn conversational editing across full clips.
- Google says references, characters, objects and scenes remain more consistent.
- The model is generally available through the Gemini API and Gemini for business.
Longer clips and lower generation costs
Gemini Omni 1.2 Flash is generally available across the Gemini API and Gemini for business, according to Google. The model can generate and edit videos natively for between 3 and 15 seconds, with duration selectable in one-second increments. That compares with a maximum of 10 seconds for Gemini Omni 1.1.
Google says users can draft at 360p or 720p, make corrections through follow-up edits and upscale selected creations to 1080p or 4K. The company lists the price for 720p video at $0.07 per second, following a 30% reduction from the previous model.
More control over references, edits and motion
The model can combine character, product or style images with short motion clips of up to three seconds and audio cues. Google says Gemini Omni 1.2 Flash keeps faces, garments, packaging typography and brand colors more consistent across camera angles. The company highlights potential uses including virtual try-on clips, catalog spins, product explainers and branded video ads.
Users can refine a clip turn by turn rather than regenerate it from scratch. Prompts can swap a product or background, change lighting or weather, or alter the aspect ratio while preserving elements of the existing video. Google says multi-turn conversational editing works across full 15-second clips.
Google also describes more natural-sounding dialogue, clearer lip-sync and distinct multi-speaker conditioning. The model supports continuous camera movements, including FPV flythroughs, zoom-outs and orbits, with fewer unwanted jump cuts, according to the company.
Availability across Google products
Developers can access Gemini Omni 1.2 Flash through the Gemini API, prototype in Google AI Studio and use Google Cloud for enterprise solutions. Google says Provisioned Throughput is available, while outputs carry an imperceptible SynthID watermark.
The model is rolling out across Google's products and developer platforms. Businesses can use it in the Google Cloud console and Gemini for business. Users of Google apps can direct scenes and make multi-turn edits in Flow, create 15-second clips at no additional cost in Google Vids with a Google account or Google Workspace subscription, and create 15-second videos in the Gemini app as the feature rolls out to Google AI Ultra subscribers.
Google says development is continuing on areas including fast sports action, rapid script changes and complex physics. For now, it positions Gemini Omni 1.2 Flash for businesses, developers and creators producing video at scale, with longer single generations and iterative editing aimed at reducing repeated work.
